def execute_script():
# imports a XES event log
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
# converts the log into a list of events (not anymore grouped in cases)
event_stream = pm4py.convert_to_event_stream(log)
# calculates a process tree using the IMf algorithm (30% noise)
net, im, fm = pm4py.discover_petri_net_inductive(log, noise_threshold=0.3)
# creates a live event stream (an object that distributes the messages to the algorithm)
live_stream = LiveEventStream()
# creates the TBR streaming conformance checking object
conf_obj = streaming_tbr.apply(net, im, fm)
# register the conformance checking object to the live event stream
live_stream.register(conf_obj)
# start the recording of events from the live event stream
live_stream.start()
# append each event of the original log to the live event stream
# (so it is sent to the conformance checking algorithm)
for index, event in enumerate(event_stream):
live_stream.append(event)
#time.sleep(5)
# stops the live event stream
live_stream.stop()
# sends a termination signal to the conformance checking algorithm;
# the conditions on the closure of all the cases are checked
# (for each case, it is checked whether the final marking is reached)
diagn_df = conf_obj.get()
conf_obj.terminate_all()
print(diagn_df)
print(diagn_df[diagn_df["is_fit"] == False])
def execute_script():
# imports a XES event log
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
# converts the log into a list of events (not anymore grouped in cases)
event_stream = pm4py.convert_to_event_stream(log)
# creates a live event stream (an object that distributes the messages to the algorithm)
live_stream = LiveEventStream()
# creates the streaming DFG discovery object
stream_dfg_disc = dfg_discovery.apply()
# register the discovery algorithm to the stream
live_stream.register(stream_dfg_disc)
# start the recording of events from the live event stream
live_stream.start()
# append each event of the original log to the live event stream
# (so it is sent to the conformance checking algorithm)
for event in event_stream:
live_stream.append(event)
# stops the live event stream
live_stream.stop()
# gets the DFG along with the start and end activities from the stream
dfg, activities, start_activities, end_activities = stream_dfg_disc.get()
# visualize the DFG
gviz = dfg_visualizer.apply(dfg,
variant=dfg_visualizer.Variants.FREQUENCY,
activities_count=activities,
parameters={
"format": "svg",
"start_activities": start_activities,
"end_activities": end_activities
})
dfg_visualizer.view(gviz)
def execute_script():
# imports a XES event log
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
# converts the log into a list of events (not anymore grouped in cases)
event_stream = pm4py.convert_to_event_stream(log)
# calculates a process tree using the IMf algorithm (50% noise)
tree = pm4py.discover_tree_inductive(log, noise_threshold=0.5)
# discovers the footprint matrix from the process tree
footprints = fp_discovery.apply(tree)
# creates a live event stream (an object that distributes the messages to the algorithm)
live_stream = LiveEventStream()
# creates the TBR streaming conformance checking object
conf_obj = streaming_fp_conf.apply(footprints)
# register the conformance checking object to the live event stream
live_stream.register(conf_obj)
# start the recording of events from the live event stream
live_stream.start()
# append each event of the original log to the live event stream
# (so it is sent to the conformance checking algorithm)
for event in event_stream:
live_stream.append(event)
# stops the live event stream
live_stream.stop()
# sends a termination signal to the conformance checking algorithm;
# the conditions on the closure of all the cases are checked
# (for each case, it is checked whether the end activity of the case
# is possible according to the footprints)
diagn_df = conf_obj.get()
conf_obj.terminate_all()
print(diagn_df)
print(diagn_df[diagn_df["is_fit"] == False])
def test_csv(self):
df = pd.read_csv("input_data/running-example.csv")
df = pm4py.format_dataframe(df, case_id="case:concept:name", activity_key="concept:name",
timestamp_key="time:timestamp")
log2 = pm4py.convert_to_event_log(df)
stream1 = pm4py.convert_to_event_stream(log2)
df2 = pm4py.convert_to_dataframe(log2)
pm4py.write_xes(log2, "test_output_data/log.xes")
os.remove("test_output_data/log.xes")
def execute_script():
log = pm4py.read_xes("../tests/input_data/receipt.xes")
static_stream = pm4py.convert_to_event_stream(log)
temporal_profile = temporal_profile_disc.apply(log)
cc = streaming_temporal_conformance.apply(temporal_profile)
live_stream = LiveEventStream()
live_stream.register(cc)
live_stream.start()
for index, ev in enumerate(static_stream):
live_stream.append(ev)
live_stream.stop()
print(cc.get())
def rebase(
log_obj: Union[EventLog, EventStream, pd.DataFrame],
case_id: str = constants.CASE_CONCEPT_NAME,
activity_key: str = xes_constants.DEFAULT_NAME_KEY,
timestamp_key: str = xes_constants.DEFAULT_TIMESTAMP_KEY,
start_timestamp_key: str = xes_constants.DEFAULT_START_TIMESTAMP_KEY):
"""
Re-base the log object, changing the case ID, activity and timestamp attributes.
Parameters
-----------------
log_obj
Log object
case_id
Case identifier
activity_key
Activity
timestamp_key
Timestamp
start_timestamp_key
Start timestamp
Returns
-----------------
rebased_log_obj
Rebased log object
"""
import pm4py
if isinstance(log_obj, pd.DataFrame):
return format_dataframe(log_obj,
case_id=case_id,
activity_key=activity_key,
timestamp_key=timestamp_key,
start_timestamp_key=start_timestamp_key)
elif isinstance(log_obj, EventLog):
log_obj = pm4py.convert_to_dataframe(log_obj)
log_obj = format_dataframe(log_obj,
case_id=case_id,
activity_key=activity_key,
timestamp_key=timestamp_key,
start_timestamp_key=start_timestamp_key)
from pm4py.objects.conversion.log import converter
return converter.apply(log_obj,
variant=converter.Variants.TO_EVENT_LOG)
elif isinstance(log_obj, EventStream):
log_obj = pm4py.convert_to_dataframe(log_obj)
log_obj = format_dataframe(log_obj,
case_id=case_id,
activity_key=activity_key,
timestamp_key=timestamp_key,
start_timestamp_key=start_timestamp_key)
return pm4py.convert_to_event_stream(log_obj)
def get_resource_count(log, mydict):
result_list = []
# This part differentiates between csv and xes files
# Event logs have a 'origin' key in their attributes dictionary that stores what type of file they came from
if log.attributes['origin'] == 'csv':
activity_str = 'concept:name'
resource_str = 'resource'
elif log.attributes['origin'] == 'xes':
activity_str = 'concept:name'
resource_str = 'org:resource'
for i in mydict['activity']:
counter = 0
check_list = []
event_stream = pm4py.convert_to_event_stream(log)
event_stream_temp = functools.filter_(lambda t: t[activity_str] == i,
event_stream)
for e in event_stream_temp:
if e[resource_str] not in check_list:
check_list.append(e[resource_str])
counter += 1
result_list.append(counter)
return result_list
def execute_script():
ENABLE_VISUALIZATION = True
# reads a XES into an event log
log1 = pm4py.read_xes("../tests/input_data/running-example.xes")
# reads a CSV into a dataframe
df = pd.read_csv("../tests/input_data/running-example.csv")
# formats the dataframe with the mandatory columns for process mining purposes
df = pm4py.format_dataframe(df,
case_id="case:concept:name",
activity_key="concept:name",
timestamp_key="time:timestamp")
# converts the dataframe to an event log
log2 = pm4py.convert_to_event_log(df)
# converts the log read from XES into a stream and dataframe respectively
stream1 = pm4py.convert_to_event_stream(log1)
df2 = pm4py.convert_to_dataframe(log1)
# writes the log1 to a XES file
pm4py.write_xes(log1, "ru1.xes")
dfg, dfg_sa, dfg_ea = pm4py.discover_dfg(log1)
petri_alpha, im_alpha, fm_alpha = pm4py.discover_petri_net_alpha(log1)
petri_inductive, im_inductive, fm_inductive = pm4py.discover_petri_net_inductive(
log1)
petri_heuristics, im_heuristics, fm_heuristics = pm4py.discover_petri_net_heuristics(
log1)
tree_inductive = pm4py.discover_tree_inductive(log1)
heu_net = pm4py.discover_heuristics_net(log1)
pm4py.write_dfg(dfg, dfg_sa, dfg_ea, "ru_dfg.dfg")
pm4py.write_petri_net(petri_alpha, im_alpha, fm_alpha, "ru_alpha.pnml")
pm4py.write_petri_net(petri_inductive, im_inductive, fm_inductive,
"ru_inductive.pnml")
pm4py.write_petri_net(petri_heuristics, im_heuristics, fm_heuristics,
"ru_heuristics.pnml")
pm4py.write_process_tree(tree_inductive, "ru_inductive.ptml")
dfg, dfg_sa, dfg_ea = pm4py.read_dfg("ru_dfg.dfg")
petri_alpha, im_alpha, fm_alpha = pm4py.read_petri_net("ru_alpha.pnml")
petri_inductive, im_inductive, fm_inductive = pm4py.read_petri_net(
"ru_inductive.pnml")
petri_heuristics, im_heuristics, fm_heuristics = pm4py.read_petri_net(
"ru_heuristics.pnml")
tree_inductive = pm4py.read_process_tree("ru_inductive.ptml")
pm4py.save_vis_petri_net(petri_alpha, im_alpha, fm_alpha, "ru_alpha.png")
pm4py.save_vis_petri_net(petri_inductive, im_inductive, fm_inductive,
"ru_inductive.png")
pm4py.save_vis_petri_net(petri_heuristics, im_heuristics, fm_heuristics,
"ru_heuristics.png")
pm4py.save_vis_process_tree(tree_inductive, "ru_inductive_tree.png")
pm4py.save_vis_heuristics_net(heu_net, "ru_heunet.png")
pm4py.save_vis_dfg(dfg, dfg_sa, dfg_ea, "ru_dfg.png")
if ENABLE_VISUALIZATION:
pm4py.view_petri_net(petri_alpha, im_alpha, fm_alpha, format="svg")
pm4py.view_petri_net(petri_inductive,
im_inductive,
fm_inductive,
format="svg")
pm4py.view_petri_net(petri_heuristics,
im_heuristics,
fm_heuristics,
format="svg")
pm4py.view_process_tree(tree_inductive, format="svg")
pm4py.view_heuristics_net(heu_net, format="svg")
pm4py.view_dfg(dfg, dfg_sa, dfg_ea, format="svg")
aligned_traces = pm4py.conformance_alignments(log1, petri_inductive,
im_inductive, fm_inductive)
replayed_traces = pm4py.conformance_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
fitness_tbr = pm4py.evaluate_fitness_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
print("fitness_tbr", fitness_tbr)
fitness_align = pm4py.evaluate_fitness_alignments(log1, petri_inductive,
im_inductive,
fm_inductive)
print("fitness_align", fitness_align)
precision_tbr = pm4py.evaluate_precision_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
print("precision_tbr", precision_tbr)
precision_align = pm4py.evaluate_precision_alignments(
log1, petri_inductive, im_inductive, fm_inductive)
print("precision_align", precision_align)
print("log start activities = ", pm4py.get_start_activities(log2))
print("df start activities = ", pm4py.get_start_activities(df2))
print("log end activities = ", pm4py.get_end_activities(log2))
print("df end activities = ", pm4py.get_end_activities(df2))
print("log attributes = ", pm4py.get_attributes(log2))
print("df attributes = ", pm4py.get_attributes(df2))
print("log org:resource values = ",
pm4py.get_attribute_values(log2, "org:resource"))
print("df org:resource values = ",
pm4py.get_attribute_values(df2, "org:resource"))
print("start_activities len(filt_log) = ",
len(pm4py.filter_start_activities(log2, ["register request"])))
print("start_activities len(filt_df) = ",
len(pm4py.filter_start_activities(df2, ["register request"])))
print("end_activities len(filt_log) = ",
len(pm4py.filter_end_activities(log2, ["pay compensation"])))
print("end_activities len(filt_df) = ",
len(pm4py.filter_end_activities(df2, ["pay compensation"])))
print(
"attributes org:resource len(filt_log) (cases) cases = ",
len(
pm4py.filter_attribute_values(log2,
"org:resource", ["Ellen"],
level="case")))
print(
"attributes org:resource len(filt_log) (cases) events = ",
len(
pm4py.filter_attribute_values(log2,
"org:resource", ["Ellen"],
level="event")))
print(
"attributes org:resource len(filt_df) (events) cases = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="case")))
print(
"attributes org:resource len(filt_df) (events) events = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="event")))
print(
"attributes org:resource len(filt_df) (events) events notpositive = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="event",
retain=False)))
print("variants log = ", pm4py.get_variants(log2))
print("variants df = ", pm4py.get_variants(df2))
print(
"variants filter log = ",
len(
pm4py.filter_variants(log2, [[
"register request", "examine thoroughly", "check ticket",
"decide", "reject request"
]])))
print(
"variants filter df = ",
len(
pm4py.filter_variants(df2, [[
"register request", "examine thoroughly", "check ticket",
"decide", "reject request"
]])))
print("variants filter percentage = ",
len(pm4py.filter_variants_percentage(log2, threshold=0.8)))
print(
"paths filter log len = ",
len(
pm4py.filter_directly_follows_relation(
log2, [("register request", "examine casually")])))
print(
"paths filter dataframe len = ",
len(
pm4py.filter_directly_follows_relation(
df2, [("register request", "examine casually")])))
print(
"timeframe filter log events len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="events")))
print(
"timeframe filter log traces_contained len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_contained")))
print(
"timeframe filter log traces_intersecting len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_intersecting")))
print(
"timeframe filter df events len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="events")))
print(
"timeframe filter df traces_contained len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_contained")))
print(
"timeframe filter df traces_intersecting len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_intersecting")))
# remove the temporary files
os.remove("ru1.xes")
os.remove("ru_dfg.dfg")
os.remove("ru_alpha.pnml")
os.remove("ru_inductive.pnml")
os.remove("ru_heuristics.pnml")
os.remove("ru_inductive.ptml")
os.remove("ru_alpha.png")
os.remove("ru_inductive.png")
os.remove("ru_heuristics.png")
os.remove("ru_inductive_tree.png")
os.remove("ru_heunet.png")
os.remove("ru_dfg.png")